CPZAI MCP Server

Endpoint

Hosted endpoint · transport streamable-http

Connect

This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

Tools

• list_strategies — status, strategy_type, title
• get_strategy — Read one strategy
• create_strategy — Create a strategy
• update_strategy — Update selected strategy fields
• list_overlays — Every overlay strategy with its hedge policy and targets
• get_overlay_exposure — What an overlay hedges, its hedge ratio, and a suggested rebalance
• configure_overlay — Set or remove an overlay's policy and targets
• get_backtest_results — List saved backtest runs
• get_backtest_result — Read one saved backtest run
• list_orders — status, symbol, side, strategy_id
• get_order — Read one CPZ order record
• place_order — Submit an order to the selected connected account
• list_positions — account_id, symbol
• sync_portfolio — Synchronize connected broker portfolios
• export_transactions — Export an account's transactions for a date range
• list_accounts — broker, environment, tradable
• cash_summary — Cash balances across your connected accounts
• list_watchlist — Read your watchlist
• add_to_watchlist — Add a symbol to your watchlist
• remove_from_watchlist — Remove a symbol from your watchlist
• list_connections — connection_type
• create_connection — Store an encrypted provider credential
• list_data_files — name, status, file_type
• get_data_file — Read uploaded file metadata
• get_market_data — Fetch current quotes for symbols
• get_bars — Fetch historical OHLCV bars
• compute_risk — Compute and store a fresh risk snapshot
• list_risk_snapshots — account_id
• get_risk_snapshot — Read one saved risk snapshot
• execute_strategy — Execute strategy code; may place orders
• list_deals — entity_id, fund, book, deal_id, product_kind, status
• list_lifecycle_events — entity_id, deal_id, kind, status, from, to
• list_cash_flows — entity_id, deal_id, fund, book, from, to, unsettled
• list_journal_entries — entity_id, deal_id, from, to
• list_fund_periods — entity_id, fund, status
• list_webhooks — active
• create_webhook — Subscribe an HTTPS endpoint to events
• delete_webhook — Remove a webhook subscription
• get_profile — Read your authenticated profile

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.

Work with this as data

Every MCP server here is available over the APIs.io API and to AI agents over MCP.

curl "https://apis.io/api/v1/mcp/cpzai-mcp-server"

curl "https://apis.io/api/v1/mcp?limit=25"